deepseek/r1-distill-qwen-7b
NewA 2026-native reasoning model distilled from R1. Specialized for agentic "Chain of Thought" logic on local hardware.
reasoningagenticdistilled
Analytics loading...
Similar Models
unsloth/LFM2-700M-GGUF
NewLiquid AI hybrid architecture via Unsloth. 700M params, 32K context, CPU-optimized. Built for narrow-scope agentic tasks: data extraction, RAG, multi-turn workflows.
ultra-smallagenticcpu-optimized
unsloth/Qwen3-4B-Instruct-2507-GGUF
NewAlibaba Qwen3 updated 4B instruct model. 256K native context, Apache 2.0. Optimized for instruction-following, tool-calling, and agentic workflows without CoT overhead.
instruction-tunedtool-callinglong-context
DeepSeek V4
deepseek/deepseek-v4
The mid-2026 flagship using Engram memory architecture, specializing in 1M+ token code generation and autonomous refactoring.
How to Use
To get started, install the `transformers` library:
pip install transformersThen, use the following snippet to load the model:
from transformers import AutoTokenizer, AutoModelForCausalLM
model_id = "deepseek/deepseek-v4"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)
# Your inference code here...Available Versions
| Tag / Variant | Size | Format | Download |
|---|---|---|---|
| deepseek/deepseek-v4:BF16 | 685GB | SafeTensors | Link |
Model Details
Teacher Model
Original Architecture (Engram)
Distillation Method
Knowledge Distillation (Logits)
Training Dataset
Flickr30k (Conceptual)
Primary Task
Multimodal Generation
Performance Metrics (Example)
| Metric | Student Model | Teacher Model |
|---|---|---|
| Model Size | 685B | 8.5GB |
| BLEU Score | 28.5 | 30.1 |